Supercharge Your AI with VoltageGPU API
Introduction
RESTful API
Our API follows REST principles with predictable resource-oriented URLs, standard HTTP verbs, and JSON responses for seamless integration.
Version Control
API versioning ensures backward compatibility. Always use the latest stable version for new projects to access the newest features.
Webhooks
Real-time event notifications keep your application in sync with GPU instance states, billing events, and system updates.
Base URL & Endpoints
https://api.voltagegpu.com/v1Authentication & Security
Secure your API requests with our token-based authentication system. Generate and manage API keys from your dashboard with granular permissions.
Generate API Key
Create keys in your dashboard
Add to Headers
Include in Authorization header
Make Requests
Start using the API
Authorization: Bearer YOUR_API_KEY_HERE- Never expose API keys in client-side code or public repositories
- Use environment variables to store sensitive credentials
- Rotate keys regularly and revoke unused ones
- Set IP whitelist and rate limits for production keys
Quick Start Guide
Create your first GPU instance in seconds
Choose your preferred programming language and follow our interactive examples to deploy your first GPU instance.
curl -X POST https://api.voltagegpu.com/v1/compute/instances \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"gpu_type": "RTX_4090",
"gpu_count": 4,
"region": "us-east-1",
"image": "pytorch:latest"
}'Core Resources
Explore the API resources for confidential GPU compute, TEE inference, and platform management
GPU Instances
Deploy and manage high-performance GPU instances with support for RTX 4090, A100, H100, and latest models.
Compute Tasks
Run containerized workloads with full Docker and Kubernetes support for scalable ML training and inference.
AI Generation
Generate images, videos, and other content using state-of-the-art AI models powered by our GPU infrastructure.
Templates
Use pre-configured templates for common workloads or create custom templates for your specific requirements.
HTTP Response Codes
VoltageGPU uses conventional HTTP response codes to indicate the success or failure of API requests. Codes in the 2xx range indicate success, 4xx indicate client errors, and 5xx indicate server errors.
Success Codes
Request completed successfully
Resource created successfully
Request succeeded with no response body
Client Errors
Invalid request parameters
Missing or invalid API key
Insufficient permissions
Resource doesn't exist
Rate limit exceeded
Server Errors
Server encountered an error
Service temporarily offline